Skip to main content

Coherence measure based on average use of formulas

  • Foundation of AI
  • Conference paper
  • First Online:

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 1531))

Abstract

Coherence is a positive virtue of theories, and its importance in theory construction is beyond debate. Unfortunately, however, a rigorous and computable definition of coherence is conspicuously lacking in the literature. This paper attempts to remedy this situation by formalising this notion of coherence and suggesting a measure. Roughly speaking, we suggest that a theory is coherent to the degree that its members (read formulas) are required to account for the intended class of observations. This approach is motivated by Bonjour’s account of coherence. We also generalise this notion of coherence to work in the context of a potentially infinite long sequence of observations.

This is a preview of subscription content, log in via an institution.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. L. Bonjour. The Structure of Empirical Knowledge. Harvard University Press, 1985.

    Google Scholar 

  2. W. Craig. On axiomatizability within a system. In The Journal of Symbolic Logic vol. 18, pages 30–32, 1953.

    Google Scholar 

  3. W. Craig. Replacement of auxilliary expressions. In Philosophical Review, 55(1), pages 38–55, 1956.

    Google Scholar 

  4. Adolf Grünbaum. The falsifiability of lorentz-fitzerald contraction hypothesis. In British Journal of The Philosophy of Science, 39, pages 48–50, 1959.

    Google Scholar 

  5. Keith Lehrer. The Theory of Knowledge. Routledge, London, 1990.

    Google Scholar 

  6. S. Muggleton and W. Buntine. Machine invention of first-order predicates by inverting resolution. In Proceedings of the 5th International Machine Learning Workshop, pages 339–352. Morgan Kaufman, 1988.

    Google Scholar 

  7. S. Muggleton and C. Feng. Efficient induction of logic programs. In Proceedings of the Fifth International Conference on Machine Learning. Morgan Kaufman, 1990.

    Google Scholar 

  8. Karl R. Popper. The Logic of Scientific Discovery. London: Hutchinson, 1968.

    Google Scholar 

  9. W. V. Quine. Word and Object. MIT Press, 1960.

    Google Scholar 

  10. W. V. Quine. On the reasons for indeterminacy of translation. In The Journal of Philosphy, LXVII 6, pages 178–183, 1970.

    Google Scholar 

  11. Ross Quinlan. Simplifying decision trees. In International Journal of Man-Machine Studies 27, pages 221–234, 1987.

    Google Scholar 

  12. Ross Quinlan. Learning logical definitions from relations. In Machine Learing, 5(3), pages 239–266, 1990.

    Google Scholar 

  13. J. R. Quinlan. C4.5: Programs For Machine Learning. Morgan Kaufmann, 1993.

    Google Scholar 

  14. P. Thagard. Explanatory coherence. In Behavioural and Brain Sciences, 12, pages 435–467, 1989.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Hing-Yan Lee Hiroshi Motoda

Rights and permissions

Reprints and permissions

Copyright information

© 1998 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Kwok, R., Nayak, A., Foo, N. (1998). Coherence measure based on average use of formulas. In: Lee, HY., Motoda, H. (eds) PRICAI’98: Topics in Artificial Intelligence. PRICAI 1998. Lecture Notes in Computer Science, vol 1531. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0095300

Download citation

  • DOI: https://doi.org/10.1007/BFb0095300

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-65271-7

  • Online ISBN: 978-3-540-49461-4

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics